Content Mining And Visualization Of Tan Yankai’s Diary

Driven by the wave of digitization,the development of digital humanities is changing with each passing day,and the constantly updated and iterative intelligent tools provide new perspectives for humanities research.The traditional humanities research paradigm has undergone cross-industry integration,transformation and innovation,and digital technology has broadened the connotation and outer boundaries of humanities research with a multi-dimensional and broad perspective,giving it new vitality.Massive digital resources need to be further explored for their humanistic connotations,providing data support for digital humanistic research.As a component of archive resources,celebrity diaries have their unique archive value and significance.In the early days of the Republic of China,the current situation was turbulent and many heroes rose up.As an important member of the military and political circles during that period,Tan Yankai not only kept the mark of his work and life,but also recorded his views and opinions on people and current affairs in the Tan Yankai’s Diary.This article takes Tan Yankai’s Diary as the research object,combs the characters and places in the diary text from 1923 to 1926 as the research data to construct a visual map of the relationship between the characters and the geographic location,and on this basis combines historical events to the relationship between the characters contained in the diary,Mining and analysis of action routes and regional hotspots,so as to show the process of Tan Yankai’s Diary from text and data to knowledge.This article first elaborates the background of the topic and the significance of the research.Through literature research,it reviews and summarizes the research on the content mining and visualization of archive resources at home and abroad,and introduces the research content,methods,tools and innovations of this article.Then,it discusses the theoretical basis of this article,such as digital humanities and visualization.On this basis,the core part of this article is divided into two chapters.The content of the first core chapter is to extract the character entity elements from the text of Tan Yankai’s Diary as research data,and use visualization tools to construct the diary character co-occurrence relationship map and the map uses social network analysis methods to analyze network characteristics,character centrality,and character groups,and explore the relationship between characters in the diary;the second core chapter is to extract the location entity elements from the text of Tan Yankai’s Diary as research Data,and establish its mapping with the date,use geographic information visualization tools to draw a map of Tan Yankai’s action route and a regional hotspot map combined with current events recorded in the diary,and analyze the cause of the formation of action routes and regional hotspots based on historical documents.Finally,summarize the research enlightenment of this article,explain the imperfections in the article,and put forward the prospect of future research directions.